An alternative for one-hot encoding in neural network models
This addresses a specific technical issue in neural network preprocessing for researchers and practitioners, but appears incremental as it offers an alternative to existing methods like one-hot encoding.
The paper tackles the problem of encoding categorical features in neural networks by proposing a binary encoding algorithm that modifies forward and backpropagation to ensure weight changes for a category only affect instances of that same category, similar to one-hot encoding.
This paper proposes an algorithm that implements binary encoding of the categorical features of neural network model input data, while also implementing changes in the forward and backpropagation procedures in order to achieve the property of having model weight changes, that result from the neural network learning process for certain data instances of some feature category, only affect the forward pass calculations for input data instances of that same feature category, as it is in the case of utilising one-hot encoding for categorical features.